/// <summary> /// 获取页面的html代码 /// </summary> /// <param name="url"></param> /// <returns></returns> private static string GetHtml(string url) { HttpHelper http = new HttpHelper(); HttpItem item = new HttpItem() { URL = url,//URL 必需项 Encoding = null,//编码格式(utf-8,gb2312,gbk) 可选项 默认类会自动识别 //Encoding = Encoding.Default, Method = "get",//URL 可选项 默认为Get Timeout = 100000,//连接超时时间 可选项默认为100000 ReadWriteTimeout = 30000,//写入Post数据超时时间 可选项默认为30000 IsToLower = false,//得到的HTML代码是否转成小写 可选项默认转小写 Cookie = "Ovo6_2132_saltkey=iuIa5B92; Ovo6_2132_lastvisit=1466129853; Ovo6_2132_lastact=1466133489%09member.php%09logging; PHPSESSID=k4bvr9rhf9dves1vtacs7vogo3; Ovo6_2132_forum_lastvisit=D_30_1466133453; Ovo6_2132_visitedfid=30; Ovo6_2132_sendmail=1; Ovo6_2132_viewid=tid_4067122; Ovo6_2132_ulastactivity=1466133489%7C0; Ovo6_2132_auth=3e80uPjE6JKYGkDyXXVwlWV8t0onQw1T3xl0U7lqoznjYnLCRalECH5zxfBzKpAFw6R2%2FJuv3hOEQCSjoKk7udCT2b7P; Ovo6_2132_lastcheckfeed=3100874%7C1466133489; Ovo6_2132_checkfollow=1",//字符串Cookie 可选项 UserAgent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.82 Safari/537.36 Edge/14.14342",//用户的浏览器类型,版本,操作系统 可选项有默认值 Accept = "text/html, application/xhtml+xml, image/jxr, */*",// 可选项有默认值 ContentType = "text/html",//返回类型 可选项有默认值 Referer = "http://hk-pic.com/thread-4067122-1-1.html",//来源URL 可选项 Allowautoredirect = true,//是否根据301跳转 可选项 //CerPath = "d:\\123.cer",//证书绝对路径 可选项不需要证书时可以不写这个参数 Connectionlimit = 1024,//最大连接数 可选项 默认为1024 //Postdata = "C:\\PERKYSU_20121129150608_ScrubLog.txt",//Post数据 可选项GET时不需要写 //PostDataType = PostDataType.FilePath,//默认为传入String类型,也可以设置PostDataType.Byte传入Byte类型数据 //ProxyIp = "192.168.1.105:8015",//代理服务器ID 端口可以直接加到后面以:分开就行了 可选项 不需要代理 时可以不设置这三个参数 //ProxyPwd = "123456",//代理服务器密码 可选项 //ProxyUserName = "******",//代理服务器账户名 可选项 ResultType = ResultType.String,//返回数据类型,是Byte还是String //PostdataByte = System.Text.Encoding.Default.GetBytes("测试一下"),//如果PostDataType为Byte时要设置本属性的值 //CookieCollection = new System.Net.CookieCollection(),//可以直接传一个Cookie集合进来 }; //item.Header.Add("测试Key1", "测试Value1"); //item.Header.Add("测试Key2", "测试Value2"); //得到HTML代码 HttpResult result = http.GetHtml(item); //取出返回的Cookie string cookie = result.Cookie; //返回的Html内容 string html = result.Html; if (result.StatusCode == System.Net.HttpStatusCode.OK) { //表示访问成功,具体的大家就参考HttpStatusCode类 } //表示StatusCode的文字说明与描述 string statusCodeDescription = result.StatusDescription; return html; }
/// <summary> /// 设置代理 /// </summary> /// <param name="item">参数对象</param> private void SetProxy(HttpItem item) { bool isIeProxy = false; if (!string.IsNullOrWhiteSpace(item.ProxyIp)) { isIeProxy = item.ProxyIp.ToLower().Contains("ieproxy"); } if (!string.IsNullOrWhiteSpace(item.ProxyIp) && !isIeProxy) { //设置代理服务器 if (item.ProxyIp.Contains(":")) { string[] plist = item.ProxyIp.Split(':'); WebProxy myProxy = new WebProxy(plist[0].Trim(), Convert.ToInt32(plist[1].Trim())); //建议连接 myProxy.Credentials = new NetworkCredential(item.ProxyUserName, item.ProxyPwd); //给当前请求对象 request.Proxy = myProxy; } else { WebProxy myProxy = new WebProxy(item.ProxyIp, false); //建议连接 myProxy.Credentials = new NetworkCredential(item.ProxyUserName, item.ProxyPwd); //给当前请求对象 request.Proxy = myProxy; } } else if (isIeProxy) { //设置为IE代理 } else { request.Proxy = item.WebProxy; } }
/// <summary> /// 为请求准备参数 /// </summary> ///<param name="item">参数列表</param> private void SetRequest(HttpItem item) { // 验证证书 SetCer(item); if (item.IPEndPoint != null) { _IPEndPoint = item.IPEndPoint; //设置本地的出口ip和端口 request.ServicePoint.BindIPEndPointDelegate = new BindIPEndPoint(BindIPEndPointCallback); } //设置Header参数 if (item.Header != null && item.Header.Count > 0) foreach (string key in item.Header.AllKeys) { request.Headers.Add(key, item.Header[key]); } // 设置代理 SetProxy(item); if (item.ProtocolVersion != null) request.ProtocolVersion = item.ProtocolVersion; request.ServicePoint.Expect100Continue = item.Expect100Continue; //请求方式Get或者Post request.Method = item.Method; request.Timeout = item.Timeout; request.KeepAlive = item.KeepAlive; request.ReadWriteTimeout = item.ReadWriteTimeout; if (!string.IsNullOrWhiteSpace(item.Host)) { request.Host = item.Host; } if (item.IfModifiedSince != null) request.IfModifiedSince = Convert.ToDateTime(item.IfModifiedSince); //Accept request.Accept = item.Accept; //ContentType返回类型 request.ContentType = item.ContentType; //UserAgent客户端的访问类型,包括浏览器版本和操作系统信息 request.UserAgent = item.UserAgent; // 编码 encoding = item.Encoding; //设置安全凭证 request.Credentials = item.ICredentials; //设置Cookie SetCookie(item); //来源地址 request.Referer = item.Referer; //是否执行跳转功能 request.AllowAutoRedirect = item.Allowautoredirect; if (item.MaximumAutomaticRedirections > 0) { request.MaximumAutomaticRedirections = item.MaximumAutomaticRedirections; } //设置Post数据 SetPostData(item); //设置最大连接 if (item.Connectionlimit > 0) request.ServicePoint.ConnectionLimit = item.Connectionlimit; }
/// <summary> /// 设置编码 /// </summary> /// <param name="item">HttpItem</param> /// <param name="result">HttpResult</param> /// <param name="ResponseByte">byte[]</param> private void SetEncoding(HttpItem item, HttpResult result, byte[] ResponseByte) { //是否返回Byte类型数据 if (item.ResultType == ResultType.Byte) result.ResultByte = ResponseByte; //从这里开始我们要无视编码了 if (encoding == null) { Match meta = Regex.Match(Encoding.Default.GetString(ResponseByte), "<meta[^<]*charset=([^<]*)[\"']", RegexOptions.IgnoreCase); string c = string.Empty; if (meta != null && meta.Groups.Count > 0) { c = meta.Groups[1].Value.ToLower().Trim(); } if (c.Length > 2) { try { encoding = Encoding.GetEncoding(c.Replace("\"", string.Empty).Replace("'", "").Replace(";", "").Replace("iso-8859-1", "gbk").Trim()); } catch { if (string.IsNullOrEmpty(response.CharacterSet)) { encoding = Encoding.UTF8; } else { encoding = Encoding.GetEncoding(response.CharacterSet); } } } else { if (string.IsNullOrEmpty(response.CharacterSet)) { encoding = Encoding.UTF8; } else { encoding = Encoding.GetEncoding(response.CharacterSet); } } } }
/// <summary> /// 设置Post数据 /// </summary> /// <param name="item">Http参数</param> private void SetPostData(HttpItem item) { //验证在得到结果时是否有传入数据 if (!request.Method.Trim().ToLower().Contains("get")) { if (item.PostEncoding != null) { postencoding = item.PostEncoding; } byte[] buffer = null; //写入Byte类型 if (item.PostDataType == PostDataType.Byte && item.PostdataByte != null && item.PostdataByte.Length > 0) { //验证在得到结果时是否有传入数据 buffer = item.PostdataByte; }//写入文件 else if (item.PostDataType == PostDataType.FilePath && !string.IsNullOrWhiteSpace(item.Postdata)) { StreamReader r = new StreamReader(item.Postdata, postencoding); buffer = postencoding.GetBytes(r.ReadToEnd()); r.Close(); } //写入字符串 else if (!string.IsNullOrWhiteSpace(item.Postdata)) { buffer = postencoding.GetBytes(item.Postdata); } if (buffer != null) { request.ContentLength = buffer.Length; request.GetRequestStream().Write(buffer, 0, buffer.Length); } } }
/// <summary> /// 设置Cookie /// </summary> /// <param name="item">Http参数</param> private void SetCookie(HttpItem item) { if (!string.IsNullOrEmpty(item.Cookie)) request.Headers[HttpRequestHeader.Cookie] = item.Cookie; //设置CookieCollection if (item.ResultCookieType == ResultCookieType.CookieCollection) { request.CookieContainer = new CookieContainer(); if (item.CookieCollection != null && item.CookieCollection.Count > 0) request.CookieContainer.Add(item.CookieCollection); } }
/// <summary> /// 设置多个证书 /// </summary> /// <param name="item"></param> private void SetCerList(HttpItem item) { if (item.ClentCertificates != null && item.ClentCertificates.Count > 0) { foreach (X509Certificate c in item.ClentCertificates) { request.ClientCertificates.Add(c); } } }
/// <summary> /// 设置证书 /// </summary> /// <param name="item"></param> private void SetCer(HttpItem item) { if (!string.IsNullOrWhiteSpace(item.CerPath)) { //这一句一定要写在创建连接的前面。使用回调的方法进行证书验证。 ServicePointManager.ServerCertificateValidationCallback = new System.Net.Security.RemoteCertificateValidationCallback(CheckValidationResult); //初始化对像,并设置请求的URL地址 request = (HttpWebRequest)WebRequest.Create(item.URL); SetCerList(item); //将证书添加到请求里 request.ClientCertificates.Add(new X509Certificate(item.CerPath)); } else { //初始化对像,并设置请求的URL地址 request = (HttpWebRequest)WebRequest.Create(item.URL); SetCerList(item); } }
/// <summary> /// 获取数据的并解析的方法 /// </summary> /// <param name="item"></param> /// <param name="result"></param> private void GetData(HttpItem item, HttpResult result) { if (response == null) { return; } #region base //获取StatusCode result.StatusCode = response.StatusCode; //获取StatusDescription result.StatusDescription = response.StatusDescription; //获取Headers result.Header = response.Headers; //获取最后访问的URl result.ResponseUri = response.ResponseUri.ToString(); //获取CookieCollection if (response.Cookies != null) result.CookieCollection = response.Cookies; //获取set-cookie if (response.Headers["set-cookie"] != null) result.Cookie = response.Headers["set-cookie"]; #endregion #region byte //处理网页Byte byte[] ResponseByte = GetByte(); #endregion #region Html if (ResponseByte != null && ResponseByte.Length > 0) { //设置编码 SetEncoding(item, result, ResponseByte); //得到返回的HTML result.Html = encoding.GetString(ResponseByte); } else { //没有返回任何Html代码 result.Html = string.Empty; } #endregion }
/// <summary> /// 根据相传入的数据,得到相应页面数据 /// </summary> /// <param name="item">参数类对象</param> /// <returns>返回HttpResult类型</returns> public HttpResult GetHtml(HttpItem item) { //返回参数 HttpResult result = new HttpResult(); try { //准备参数 SetRequest(item); } catch (Exception ex) { //配置参数时出错 return new HttpResult() { Cookie = string.Empty, Header = null, Html = ex.Message, StatusDescription = "配置参数时出错:" + ex.Message }; } try { //请求数据 using (response = (HttpWebResponse)request.GetResponse()) { GetData(item, result); } } catch (WebException ex) { if (ex.Response != null) { using (response = (HttpWebResponse)ex.Response) { GetData(item, result); } } else { result.Html = ex.Message; } } catch (Exception ex) { result.Html = ex.Message; } if (item.IsToLower) result.Html = result.Html.ToLower(); return result; }